{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:O5Z2JGDZFE7ZEWU2SACEAXUIDR","short_pith_number":"pith:O5Z2JGDZ","schema_version":"1.0","canonical_sha256":"7773a49879293f925a9a9004405e881c48b0c8c0fa802cb3b88a53d34591396a","source":{"kind":"arxiv","id":"2506.08023","version":1},"attestation_state":"computed","paper":{"title":"Aligning Proteins and Language: A Foundation Model for Protein Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CE","cs.CV","cs.LG"],"primary_cat":"q-bio.BM","authors_text":"Daisuke Kihara, Han Zhu, Min Xu, Qifeng Wu, Yizhou Zhao, Zhengzhe Liu","submitted_at":"2025-05-27T08:13:08Z","abstract_excerpt":"This paper aims to retrieve proteins with similar structures and semantics from large-scale protein dataset, facilitating the functional interpretation of protein structures derived by structural determination methods like cryo-Electron Microscopy (cryo-EM). Motivated by the recent progress of vision-language models (VLMs), we propose a CLIP-style framework for aligning 3D protein structures with functional annotations using contrastive learning. For model training, we propose a large-scale dataset of approximately 200,000 protein-caption pairs with rich functional descriptors. We evaluate our"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2506.08023","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.BM","submitted_at":"2025-05-27T08:13:08Z","cross_cats_sorted":["cs.AI","cs.CE","cs.CV","cs.LG"],"title_canon_sha256":"0da33e7205b2525232930124a175279b9e250c42f98355946f638303d3f493a3","abstract_canon_sha256":"a365f3af5f89a5a8846dbe950b0e32d45d7f7550b1b3ff01826020d68998c7f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:43.827029Z","signature_b64":"U5TuqFWe6fI8rwq7HQOz5ZBnLYWGVvnKqnzVgii1CK2mt5cch/OatqOZPX7YNF2zQrTg0u/hcvGtIXHa7y0jBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7773a49879293f925a9a9004405e881c48b0c8c0fa802cb3b88a53d34591396a","last_reissued_at":"2026-07-05T11:18:43.826650Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:43.826650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Aligning Proteins and Language: A Foundation Model for Protein Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CE","cs.CV","cs.LG"],"primary_cat":"q-bio.BM","authors_text":"Daisuke Kihara, Han Zhu, Min Xu, Qifeng Wu, Yizhou Zhao, Zhengzhe Liu","submitted_at":"2025-05-27T08:13:08Z","abstract_excerpt":"This paper aims to retrieve proteins with similar structures and semantics from large-scale protein dataset, facilitating the functional interpretation of protein structures derived by structural determination methods like cryo-Electron Microscopy (cryo-EM). Motivated by the recent progress of vision-language models (VLMs), we propose a CLIP-style framework for aligning 3D protein structures with functional annotations using contrastive learning. For model training, we propose a large-scale dataset of approximately 200,000 protein-caption pairs with rich functional descriptors. We evaluate our"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08023","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2506.08023/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.08023","created_at":"2026-07-05T11:18:43.826700+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.08023v1","created_at":"2026-07-05T11:18:43.826700+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08023","created_at":"2026-07-05T11:18:43.826700+00:00"},{"alias_kind":"pith_short_12","alias_value":"O5Z2JGDZFE7Z","created_at":"2026-07-05T11:18:43.826700+00:00"},{"alias_kind":"pith_short_16","alias_value":"O5Z2JGDZFE7ZEWU2","created_at":"2026-07-05T11:18:43.826700+00:00"},{"alias_kind":"pith_short_8","alias_value":"O5Z2JGDZ","created_at":"2026-07-05T11:18:43.826700+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O5Z2JGDZFE7ZEWU2SACEAXUIDR","json":"https://pith.science/pith/O5Z2JGDZFE7ZEWU2SACEAXUIDR.json","graph_json":"https://pith.science/api/pith-number/O5Z2JGDZFE7ZEWU2SACEAXUIDR/graph.json","events_json":"https://pith.science/api/pith-number/O5Z2JGDZFE7ZEWU2SACEAXUIDR/events.json","paper":"https://pith.science/paper/O5Z2JGDZ"},"agent_actions":{"view_html":"https://pith.science/pith/O5Z2JGDZFE7ZEWU2SACEAXUIDR","download_json":"https://pith.science/pith/O5Z2JGDZFE7ZEWU2SACEAXUIDR.json","view_paper":"https://pith.science/paper/O5Z2JGDZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.08023&json=true","fetch_graph":"https://pith.science/api/pith-number/O5Z2JGDZFE7ZEWU2SACEAXUIDR/graph.json","fetch_events":"https://pith.science/api/pith-number/O5Z2JGDZFE7ZEWU2SACEAXUIDR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O5Z2JGDZFE7ZEWU2SACEAXUIDR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O5Z2JGDZFE7ZEWU2SACEAXUIDR/action/storage_attestation","attest_author":"https://pith.science/pith/O5Z2JGDZFE7ZEWU2SACEAXUIDR/action/author_attestation","sign_citation":"https://pith.science/pith/O5Z2JGDZFE7ZEWU2SACEAXUIDR/action/citation_signature","submit_replication":"https://pith.science/pith/O5Z2JGDZFE7ZEWU2SACEAXUIDR/action/replication_record"}},"created_at":"2026-07-05T11:18:43.826700+00:00","updated_at":"2026-07-05T11:18:43.826700+00:00"}